Merge tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd

Pull iommufd updates from Jason Gunthorpe:
 "Some polishing and small fixes for iommufd:

   - Remove IOMMU_CAP_INTR_REMAP, instead rely on the interrupt
     subsystem

   - Use GFP_KERNEL_ACCOUNT inside the iommu_domains

   - Support VFIO_NOIOMMU mode with iommufd

   - Various typos

   - A list corruption bug if HWPTs are used for attach"

* tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd:
  iommufd: Do not add the same hwpt to the ioas->hwpt_list twice
  iommufd: Make sure to zero vfio_iommu_type1_info before copying to user
  vfio: Support VFIO_NOIOMMU with iommufd
  iommufd: Add three missing structures in ucmd_buffer
  selftests: iommu: Fix test_cmd_destroy_access() call in user_copy
  iommu: Remove IOMMU_CAP_INTR_REMAP
  irq/s390: Add arch_is_isolated_msi() for s390
  iommu/x86: Replace IOMMU_CAP_INTR_REMAP with IRQ_DOMAIN_FLAG_ISOLATED_MSI
  genirq/msi: Rename IRQ_DOMAIN_MSI_REMAP to IRQ_DOMAIN_ISOLATED_MSI
  genirq/irqdomain: Remove unused irq_domain_check_msi_remap() code
  iommufd: Convert to msi_device_has_isolated_msi()
  vfio/type1: Convert to iommu_group_has_isolated_msi()
  iommu: Add iommu_group_has_isolated_msi()
  genirq/msi: Add msi_device_has_isolated_msi()

10 files changed, 122 insertions, 36 deletions

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index c20c41dd9c91..5a505ba5467e 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -2278,8 +2278,6 @@ static bool amd_iommu_capable(struct device *dev, enum iommu_cap cap)
 	switch (cap) {
 	case IOMMU_CAP_CACHE_COHERENCY:
 		return true;
-	case IOMMU_CAP_INTR_REMAP:
-		return (irq_remapping_enabled == 1);
 	case IOMMU_CAP_NOEXEC:
 		return false;
 	case IOMMU_CAP_PRE_BOOT_PROTECTION:
@@ -3682,7 +3680,8 @@ int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
 	}
 
 	irq_domain_update_bus_token(iommu->ir_domain,  DOMAIN_BUS_AMDVI);
-	iommu->ir_domain->flags |= IRQ_DOMAIN_FLAG_MSI_PARENT;
+	iommu->ir_domain->flags |= IRQ_DOMAIN_FLAG_MSI_PARENT |
+				   IRQ_DOMAIN_FLAG_ISOLATED_MSI;
 
 	if (amd_iommu_np_cache)
 		iommu->ir_domain->msi_parent_ops = &virt_amdvi_msi_parent_ops;
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 86ee06ac058b..7c2f4bd33582 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -4478,8 +4478,6 @@ static bool intel_iommu_capable(struct device *dev, enum iommu_cap cap)
 	switch (cap) {
 	case IOMMU_CAP_CACHE_COHERENCY:
 		return true;
-	case IOMMU_CAP_INTR_REMAP:
-		return irq_remapping_enabled == 1;
 	case IOMMU_CAP_PRE_BOOT_PROTECTION:
 		return dmar_platform_optin();
 	case IOMMU_CAP_ENFORCE_CACHE_COHERENCY:
diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c
index f58f5f57af78..6d01fa078c36 100644
--- a/drivers/iommu/intel/irq_remapping.c
+++ b/drivers/iommu/intel/irq_remapping.c
@@ -573,7 +573,8 @@ static int intel_setup_irq_remapping(struct intel_iommu *iommu)
 	}
 
 	irq_domain_update_bus_token(iommu->ir_domain,  DOMAIN_BUS_DMAR);
-	iommu->ir_domain->flags |= IRQ_DOMAIN_FLAG_MSI_PARENT;
+	iommu->ir_domain->flags |= IRQ_DOMAIN_FLAG_MSI_PARENT |
+				   IRQ_DOMAIN_FLAG_ISOLATED_MSI;
 
 	if (cap_caching_mode(iommu->cap))
 		iommu->ir_domain->msi_parent_ops = &virt_dmar_msi_parent_ops;
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index b3f847b25b4f..10db680acaed 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -30,6 +30,7 @@
 #include <linux/cc_platform.h>
 #include <trace/events/iommu.h>
 #include <linux/sched/mm.h>
+#include <linux/msi.h>
 
 #include "dma-iommu.h"
 
@@ -1905,6 +1906,29 @@ bool device_iommu_capable(struct device *dev, enum iommu_cap cap)
 EXPORT_SYMBOL_GPL(device_iommu_capable);
 
 /**
+ * iommu_group_has_isolated_msi() - Compute msi_device_has_isolated_msi()
+ *       for a group
+ * @group: Group to query
+ *
+ * IOMMU groups should not have differing values of
+ * msi_device_has_isolated_msi() for devices in a group. However nothing
+ * directly prevents this, so ensure mistakes don't result in isolation failures
+ * by checking that all the devices are the same.
+ */
+bool iommu_group_has_isolated_msi(struct iommu_group *group)
+{
+	struct group_device *group_dev;
+	bool ret = true;
+
+	mutex_lock(&group->mutex);
+	list_for_each_entry(group_dev, &group->devices, list)
+		ret &= msi_device_has_isolated_msi(group_dev->dev);
+	mutex_unlock(&group->mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_group_has_isolated_msi);
+
+/**
  * iommu_set_fault_handler() - set a fault handler for an iommu domain
  * @domain: iommu domain
  * @handler: fault handler
diff --git a/drivers/iommu/iommufd/Kconfig b/drivers/iommu/iommufd/Kconfig
index 8306616b6d81..ada693ea51a7 100644
--- a/drivers/iommu/iommufd/Kconfig
+++ b/drivers/iommu/iommufd/Kconfig
@@ -23,7 +23,7 @@ config IOMMUFD_VFIO_CONTAINER
 	  removed.
 
 	  IOMMUFD VFIO container emulation is known to lack certain features
-	  of the native VFIO container, such as no-IOMMU support, peer-to-peer
+	  of the native VFIO container, such as peer-to-peer
 	  DMA mapping, PPC IOMMU support, as well as other potentially
 	  undiscovered gaps.  This option is currently intended for the
 	  purpose of testing IOMMUFD with unmodified userspace supporting VFIO
diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c
index d81f93a321af..a0c66f47a65a 100644
--- a/drivers/iommu/iommufd/device.c
+++ b/drivers/iommu/iommufd/device.c
@@ -4,7 +4,6 @@
 #include <linux/iommufd.h>
 #include <linux/slab.h>
 #include <linux/iommu.h>
-#include <linux/irqdomain.h>
 
 #include "io_pagetable.h"
 #include "iommufd_private.h"
@@ -169,8 +168,7 @@ static int iommufd_device_setup_msi(struct iommufd_device *idev,
 	 * operation from the device (eg a simple DMA) cannot trigger an
 	 * interrupt outside this iommufd context.
 	 */
-	if (!device_iommu_capable(idev->dev, IOMMU_CAP_INTR_REMAP) &&
-	    !irq_domain_check_msi_remap()) {
+	if (!iommu_group_has_isolated_msi(idev->group)) {
 		if (!allow_unsafe_interrupts)
 			return -EPERM;
 
@@ -346,10 +344,6 @@ int iommufd_device_attach(struct iommufd_device *idev, u32 *pt_id)
 		rc = iommufd_device_do_attach(idev, hwpt);
 		if (rc)
 			goto out_put_pt_obj;
-
-		mutex_lock(&hwpt->ioas->mutex);
-		list_add_tail(&hwpt->hwpt_item, &hwpt->ioas->hwpt_list);
-		mutex_unlock(&hwpt->ioas->mutex);
 		break;
 	}
 	case IOMMUFD_OBJ_IOAS: {
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index 222e86591f8a..9d7f71510ca1 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -18,6 +18,8 @@ struct iommufd_ctx {
 	struct xarray objects;
 
 	u8 account_mode;
+	/* Compatibility with VFIO no iommu */
+	u8 no_iommu_mode;
 	struct iommufd_ioas *vfio_ioas;
 };
 
diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
index 083e6fcbe10a..3fbe636c3d8a 100644
--- a/drivers/iommu/iommufd/main.c
+++ b/drivers/iommu/iommufd/main.c
@@ -252,9 +252,12 @@ union ucmd_buffer {
 	struct iommu_destroy destroy;
 	struct iommu_ioas_alloc alloc;
 	struct iommu_ioas_allow_iovas allow_iovas;
+	struct iommu_ioas_copy ioas_copy;
 	struct iommu_ioas_iova_ranges iova_ranges;
 	struct iommu_ioas_map map;
 	struct iommu_ioas_unmap unmap;
+	struct iommu_option option;
+	struct iommu_vfio_ioas vfio_ioas;
 #ifdef CONFIG_IOMMUFD_TEST
 	struct iommu_test_cmd test;
 #endif
diff --git a/drivers/iommu/iommufd/vfio_compat.c b/drivers/iommu/iommufd/vfio_compat.c
index 3ceca0e8311c..514494a0025b 100644
--- a/drivers/iommu/iommufd/vfio_compat.c
+++ b/drivers/iommu/iommufd/vfio_compat.c
@@ -26,39 +26,84 @@ out_unlock:
 }
 
 /**
- * iommufd_vfio_compat_ioas_id - Return the IOAS ID that vfio should use
+ * iommufd_vfio_compat_ioas_get_id - Ensure a compat IOAS exists
+ * @ictx: Context to operate on
+ * @out_ioas_id: The IOAS ID of the compatibility IOAS
+ *
+ * Return the ID of the current compatibility IOAS. The ID can be passed into
+ * other functions that take an ioas_id.
+ */
+int iommufd_vfio_compat_ioas_get_id(struct iommufd_ctx *ictx, u32 *out_ioas_id)
+{
+	struct iommufd_ioas *ioas;
+
+	ioas = get_compat_ioas(ictx);
+	if (IS_ERR(ioas))
+		return PTR_ERR(ioas);
+	*out_ioas_id = ioas->obj.id;
+	iommufd_put_object(&ioas->obj);
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(iommufd_vfio_compat_ioas_get_id, IOMMUFD_VFIO);
+
+/**
+ * iommufd_vfio_compat_set_no_iommu - Called when a no-iommu device is attached
+ * @ictx: Context to operate on
+ *
+ * This allows selecting the VFIO_NOIOMMU_IOMMU and blocks normal types.
+ */
+int iommufd_vfio_compat_set_no_iommu(struct iommufd_ctx *ictx)
+{
+	int ret;
+
+	xa_lock(&ictx->objects);
+	if (!ictx->vfio_ioas) {
+		ictx->no_iommu_mode = 1;
+		ret = 0;
+	} else {
+		ret = -EINVAL;
+	}
+	xa_unlock(&ictx->objects);
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(iommufd_vfio_compat_set_no_iommu, IOMMUFD_VFIO);
+
+/**
+ * iommufd_vfio_compat_ioas_create - Ensure the compat IOAS is created
  * @ictx: Context to operate on
- * @out_ioas_id: The ioas_id the caller should use
  *
  * The compatibility IOAS is the IOAS that the vfio compatibility ioctls operate
  * on since they do not have an IOAS ID input in their ABI. Only attaching a
- * group should cause a default creation of the internal ioas, this returns the
- * existing ioas if it has already been assigned somehow.
+ * group should cause a default creation of the internal ioas, this does nothing
+ * if an existing ioas has already been assigned somehow.
  */
-int iommufd_vfio_compat_ioas_id(struct iommufd_ctx *ictx, u32 *out_ioas_id)
+int iommufd_vfio_compat_ioas_create(struct iommufd_ctx *ictx)
 {
 	struct iommufd_ioas *ioas = NULL;
-	struct iommufd_ioas *out_ioas;
+	int ret;
 
 	ioas = iommufd_ioas_alloc(ictx);
 	if (IS_ERR(ioas))
 		return PTR_ERR(ioas);
 
 	xa_lock(&ictx->objects);
-	if (ictx->vfio_ioas && iommufd_lock_obj(&ictx->vfio_ioas->obj))
-		out_ioas = ictx->vfio_ioas;
-	else {
-		out_ioas = ioas;
-		ictx->vfio_ioas = ioas;
+	/*
+	 * VFIO won't allow attaching a container to both iommu and no iommu
+	 * operation
+	 */
+	if (ictx->no_iommu_mode) {
+		ret = -EINVAL;
+		goto out_abort;
 	}
-	xa_unlock(&ictx->objects);
 
-	*out_ioas_id = out_ioas->obj.id;
-	if (out_ioas != ioas) {
-		iommufd_put_object(&out_ioas->obj);
-		iommufd_object_abort(ictx, &ioas->obj);
-		return 0;
+	if (ictx->vfio_ioas && iommufd_lock_obj(&ictx->vfio_ioas->obj)) {
+		ret = 0;
+		iommufd_put_object(&ictx->vfio_ioas->obj);
+		goto out_abort;
 	}
+	ictx->vfio_ioas = ioas;
+	xa_unlock(&ictx->objects);
+
 	/*
 	 * An automatically created compat IOAS is treated as a userspace
 	 * created object. Userspace can learn the ID via IOMMU_VFIO_IOAS_GET,
@@ -67,8 +112,13 @@ int iommufd_vfio_compat_ioas_id(struct iommufd_ctx *ictx, u32 *out_ioas_id)
 	 */
 	iommufd_object_finalize(ictx, &ioas->obj);
 	return 0;
+
+out_abort:
+	xa_unlock(&ictx->objects);
+	iommufd_object_abort(ictx, &ioas->obj);
+	return ret;
 }
-EXPORT_SYMBOL_NS_GPL(iommufd_vfio_compat_ioas_id, IOMMUFD_VFIO);
+EXPORT_SYMBOL_NS_GPL(iommufd_vfio_compat_ioas_create, IOMMUFD_VFIO);
 
 int iommufd_vfio_ioas(struct iommufd_ucmd *ucmd)
 {
@@ -235,6 +285,9 @@ static int iommufd_vfio_check_extension(struct iommufd_ctx *ictx,
 	case VFIO_UNMAP_ALL:
 		return 1;
 
+	case VFIO_NOIOMMU_IOMMU:
+		return IS_ENABLED(CONFIG_VFIO_NOIOMMU);
+
 	case VFIO_DMA_CC_IOMMU:
 		return iommufd_vfio_cc_iommu(ictx);
 
@@ -261,10 +314,24 @@ static int iommufd_vfio_check_extension(struct iommufd_ctx *ictx,
 
 static int iommufd_vfio_set_iommu(struct iommufd_ctx *ictx, unsigned long type)
 {
+	bool no_iommu_mode = READ_ONCE(ictx->no_iommu_mode);
 	struct iommufd_ioas *ioas = NULL;
 	int rc = 0;
 
-	if (type != VFIO_TYPE1_IOMMU && type != VFIO_TYPE1v2_IOMMU)
+	/*
+	 * Emulation for NOIOMMU is imperfect in that VFIO blocks almost all
+	 * other ioctls. We let them keep working but they mostly fail since no
+	 * IOAS should exist.
+	 */
+	if (IS_ENABLED(CONFIG_VFIO_NOIOMMU) && type == VFIO_NOIOMMU_IOMMU &&
+	    no_iommu_mode) {
+		if (!capable(CAP_SYS_RAWIO))
+			return -EPERM;
+		return 0;
+	}
+
+	if ((type != VFIO_TYPE1_IOMMU && type != VFIO_TYPE1v2_IOMMU) ||
+	    no_iommu_mode)
 		return -EINVAL;
 
 	/* VFIO fails the set_iommu if there is no group */
@@ -381,7 +448,7 @@ static int iommufd_vfio_iommu_get_info(struct iommufd_ctx *ictx,
 	};
 	size_t minsz = offsetofend(struct vfio_iommu_type1_info, iova_pgsizes);
 	struct vfio_info_cap_header __user *last_cap = NULL;
-	struct vfio_iommu_type1_info info;
+	struct vfio_iommu_type1_info info = {};
 	struct iommufd_ioas *ioas;
 	size_t total_cap_size;
 	int rc;
diff --git a/drivers/iommu/s390-iommu.c b/drivers/iommu/s390-iommu.c
index 6849644e2892..fbf59a8db29b 100644
--- a/drivers/iommu/s390-iommu.c
+++ b/drivers/iommu/s390-iommu.c
@@ -34,8 +34,6 @@ static bool s390_iommu_capable(struct device *dev, enum iommu_cap cap)
 	switch (cap) {
 	case IOMMU_CAP_CACHE_COHERENCY:
 		return true;
-	case IOMMU_CAP_INTR_REMAP:
-		return true;
 	default:
 		return false;
 	}